There are 9 repositories under scene-text topic.
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
Text recognition (optical character recognition) with deep learning methods, ICCV 2019
TextBoxes++: A Single-Shot Oriented Scene Text Detector
Total Text Dataset. It consists of 1555 images with more than 3 different text orientations: Horizontal, Multi-Oriented, and Curved, one of a kind.
ASTER in Pytorch
This repository provides train&test code, dataset, det.&rec. annotation, evaluation script, annotation tool, and ranking.
MORAN: A Multi-Object Rectified Attention Network for Scene Text Recognition
The code of "Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting"
Official Implementation of SynthTIGER (Synthetic Text Image Generator), ICDAR 2021
Geometric Augmentation for Text Image
A novel region proposal network for more general object detection ( including scene text detection ).
TextField: Learning A Deep Direction Field for Irregular Scene Text Detection (TIP 2019)
This is a c++ project deploying a deep scene text reading pipeline with tensorflow. It reads text from natural scene images. It uses frozen tensorflow graphs. The detector detect scene text locations. The recognizer reads word from each detected bounding box.
A curated list of papers and resources for scene text detection and recognition
This project modify tensorflow object detection api code to predict oriented bounding boxes. It can be used for scene text detection.
Script identification in natural scene image and video frames using an attention based Convolutional-LSTM network (Pattern Recognition, 2019)
Pytorch implementation for pixel-wise scene text segmentation based on DeepLabV3+
A Word Spotting Method in Scene Images based on Character Recognition
Making machine learning and computer vision simple.
A demo for OCR on Signboard (ArT dataset) using PaddleOCR' EAST + CRNN, MMOCR's ASTER and CRAFT.
Code for generating synthetic text images in Indic languages. Based on Ankush et al. CVPR'16.
A multi-label language identification dataset based on regional Indian languages. It contains 5 languages (Hindi, Bengali, Malayalam, Kannada, and English) with the presence of two scripts per image (implying the multi-linguality). The dataset is diverse in nature with the existence of curved, perspective distorted, and multi-oriented text in addition to the horizontal text. This diversity is achieved by applying various image transformation techniques such as affine, arcs, and perspective distortion with different angular degrees. The dataset is harvested from multiple sources: captured from mobile cameras, existing datasets, and web sources.